AI Science Tracker
EN

Machine Learning Model for Predicting Mortality Risk in Patients With Complex Chronic Conditions: Retrospective Analysis.

Research Group on Innovation; Hospital Germans Trias i Pujol Institut Català de la Salut Badalona Spain · 28 Dec 2023 · medicine

Discovery

Machine Learning Model for Predicting Mortality Risk in Patients With Complex Chronic Conditions: Retrospective Analysis.

Source check: Source checked. Not independent scientific confirmation.

Finding: Machine-learning survival models predicted mortality in patients with complex chronic conditions and identified risk patterns in retrospective records; results are population- and data-source-bound.

Technology: XGBoost and gradient-boosting survival models use clinical and healthcare-resource variables to estimate mortality in patients with complex chronic conditions.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
XGBoost and gradient-boosting survival models use clinical and healthcare-resource variables to estimate mortality in patients with complex chronic conditions.
Test and result
In a retrospective cohort, XGBoost achieved AUC 0.88 for four-year mortality prediction; prediction of early mortality was weaker, with recall 0.55.
Limitation / still unknown
Results are bounded to the analyzed population and records; prospective care impact is untested.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://doi.org/10.2196/52782 · https://europepmc.org/article/MED/38223690 · https://europepmc.org/articles/PMC10784974 · https://www.ncbi.nlm.nih.gov/research/bionlp/RESTful/pmcoa.cgi/BioC_json/PMC10784974/unicode · https://pubmed.ncbi.nlm.nih.gov/38223690/

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.